A two-piece scale mixture normal measurement error models for replicated data

Document Type : Original Article

Author

• Fereshteh Kahrari

Department of Statistical Sciences, University of Padova, Italy

10.22067/smps.2024.46110

Abstract

‎We develop a new class of flexible replicated measurement error models (RMEM) based on the normal two-piece scale mixture (TP-SMN) family to model the distribution of the latent variable‎. ‎In the proposed approach‎, ‎the replicated observations are jointly modeled by a mixture of two components from a scale mixture skew-normal (SMSN) density‎. ‎The flexibility of this class can enable the simultaneous accommodation of skewness‎, ‎outliers‎, ‎and multimodality‎. ‎The proposed connection between the unobserved covariates and the response facilitates the construction of an EM-type algorithm to perform maximum likelihood estimation‎. ‎The effectiveness of the maximum likelihood estimations is studied through the simulation studies‎. ‎Also‎, ‎the method is applied to analyze continuing survey data on food intake by individuals on diet habits‎.

Keywords

• ECM algorithm
• Equation error
• Replicated measurement error model
• Two-piece scale mixture normal

---

References

1.  Akaike, H. (1974). A new look at the statistical model identification. IEEE Transactions on Automatic
   Control, 19, 716–723.
2. Andrews, D. F. and Mallows, C. L. (1974). Scale mixtures of normal distributions. Journal of the Royal Statistical Society, Series B, 36, 99–102.
3. Arellano-Valle, R. B., Azzalini A., Ferreira C.S. and Santoro, K. (2020). A two-piece normal measurement error model. Computational Statistics & Data Analysis, 144, 106863.
4. Arellano-Valle, R. B., Gomez, H. and Quintana, F.A. (2005). Statistical inference for a general class of asymmetric distributions. Journal of Statistical Planning and Inference, 128, 427–443.
5. Arellano-Valle, R. B. and Genton, M. G. (2005). On fundamental skew distributions. Journal of Multivariate Analysis, 96, 93–116.
6. Arellano-Valle, R. B., Ozan, S., Bolfarine, H. and Lachos, V. H. (2005). Skew normal measurement error models. Journal of Multivariate Analysis, 96, 265–281.
7. Barkhordar, Z., Maleki, M., Khodadadi, Z., Wraith, D. and Negahdari, F. (2020). A Bayesian approach on the two-piece scale mixtures of normal homoscedastic nonlinear regression models. Journal of Applied Statistics, 9, 1305–1322.
8. Branco, M. D. and Dey, D. K. (2001). A general class of multivariate skew-elliptical distributions. Journal of Multivariate Analysis, 79, 99–113.
9. Buonaccorsi. J. P. (2010). Measurement Error: Models, Methods, and Applications. Chapman and Hall, Boca Raton.
10. Cao, C. Z., Lin, J. G., Shi, J. Q., Wang, W. and Zhang, X. Y. (2015). Multivariate measurement error models for replicated data under heavy-tailed distributions. Journal of Chemometrics, 29, 457–466.
11. Cao, C. Z., Wang, W., Shi, J. Q. and Lin, J. G. (2018). Measurement error models for replicated data under asymmetric heavy-tailed distributions. Computational Economics, 52, 531–553.
12. Carroll, R. J. Ruppert, D., Stefanski, L. A. and Crainiceanu, C. M. (2006). Measurement error in nonlinear models. A modern perspective (2nd edn). Chapman and Hall, Boca Raton.
13. Chan, L. K. and Mak, T. K. (1979). Maximum likelihood estimation of a linear structural relationship with replication. Journal of the Royal Statistical Society, Series B, 41, 263–268.
14. Cheng, C. L. and Van Ness, J. W. (1999). Statistical Regression with Measurement Error. Oxford University Press, London.
15. Fuller, W. A. (1987). Measurement Error Models. Wiley, New York.
16. Heteroscedastic nonlinear regression models using asymmetric and heavy tailed two-piece distributions.
    AStA Advances in Statistical Analysis, 105, 451–467.
17. Isogava, Y. (1985). Estimating a multivariate linear structural relationship with replication. Journal of the Royal Statistical Society, Series B, 47, 211–215.
18. Gustafson, P. (2004). Measurement Error and Misclassification in Statistics and Epidemiology. Chapman and Hall, Boca Raton.
19.  Ghasami, S., Maleki, M., and Khodadadi, Z. (2020). Leptokurtic and platykurtic class of robust symmetrical and asymmetrical time series models. Journal of Computational and Applied Mathematics, 376, 112806.
20. Lachos, V. H., Angolini, T., and Abanto-Valle, C. A. (2011). On estimation and local influence analysis for measurement errors models under heavy-tailed distributions. Statistical Papers, 52, 567–590.
21. Lin, N., Bailey, B. A. and He, X. M. (2004). Adjustment of measuring devices with linear models. Technometrics, 46, 127–134.
22. Lin, J. G. and Cao, C. Z. (2013). On estimation of measurement error models with replication under heavy-tailed distributions. Computational Statistics, 28, 802–829.
23. Louis, T. A. (1982). Finding the observed information matrix when using the EM algorithm. Journal of the Royal Statistical Society, Series B, 44, 226–233.
24. Maleki, M., Barkhordar, Z., Khodadadi, Z., and Wraith, D. (2019c). A robust class of homoscedastic nonlinear regression models. Journal of Statistical Computation and Simulation, 89, 2765–2781.
25. Maleki, M., Contreras-Reyes, J. E., and Mahmoudi, M. R. (2019d). Robust mixture modeling based on two-piece scale mixtures of normal family. Axioms, 8, 38.
26. Maleki, M., and Mahmoudi, M. R. (2017). Two-piece location-scale distributions based on scale mixtures of normal family. Communications in Statistics-Theory and Methods, 46, 12356–12369.
27. Meng, X. L., and Rubin, D. B. (1993). Maximum likelihood estimation via the EM algorithm: a general framework. Biometrika, 80, 267–278.
28. Moravveji, B., Khodadadi, Z., and Maleki, M. (2019). A Bayesian analysis of two-piece distributions based on the scale mixtures of normal family. Iranian Journal of Science and Technology, Transactions A: Science, 43, 991–1001.
29. Reiersol, O. (1950). Identifibility of a linear relation between variables which are subject to errors. Econometrica, 18, 375–389.
30. Schwarz, G. (1978). Estimating the dimension of a model. Annals of Statistics, 6, 461–464.
31. Zarei, A., Khodadadi, Z., Maleki, M. and Zare, K. (2022). Robust mixture regression modeling based on two-piece scale mixtures of normal distributions. Advances in Data Analysis and Classifiation, 17, 181–210.